NeuPortal blog
AI × Markets, in plain English
Clear guides as we build in the open — knowledge, never signals.
-
The Base Rate Fallacy: Why Good Forecasters Start With Frequency
Ignoring how often something usually happens is one of the most common forecasting mistakes. What the base rate fallacy is, the classic example, and how good forecasters avoid it.
Read → -
What Is the CRPS? Grading a Whole Probability Distribution
The Brier score grades a probability for a yes/no event. The CRPS does the same job for a full distribution over a number. Here is how it works and why it is a proper scoring rule.
Read → -
NeuPortal Enters the Arena: Competing in Public AI Forecasting Championships
We put our forecasting where it can be independently scored: NeuPortal has entered public AI forecasting arenas, shipped an honest benchmark, and measured a real improvement.
Read → -
Overfitting: Why a Great Backtest Can Still Lose in the Real World
A model that looks spectacular on historical data is the easiest thing to build and the hardest to trust. What overfitting is, why it fools you, and the only test that cannot be gamed.
Read → -
Expected Value in Forecasting: Turning Probabilities Into an Edge
A forecast becomes useful only when you compare its probability to a price. Here is how expected value works, why positive EV is never a promise, and the calibration it depends on.
Read → -
The Wisdom of Crowds: Why Aggregated Forecasts Beat Lone Experts
Why the average of many independent guesses often beats the sharpest lone expert — the statistics behind the wisdom of crowds and why prediction markets exploit it.
Read → -
How Prediction Markets Aggregate Information
Prediction markets turn scattered beliefs into a probability estimate. Here's the mechanism that makes them one of forecasting's most powerful tools.
Read → -
Log Loss vs Brier Score: Two Ways to Grade a Probabilistic Forecast
Log loss vs Brier score explained: how each grades a probabilistic forecast, why log loss punishes confident errors harder, and when to use which metric.
Read → -
How AI Reads Crypto Volatility Regimes (and Why It Won't Predict Price)
How AI detects crypto volatility regimes using realized volatility, clustering, and time-series models — and why the honest output is uncertainty, not price targets.
Read → -
Monte Carlo Simulation for Tournament Forecasting: From a Match Model to Bracket Probabilities
How to run thousands of simulated tournaments to turn a single-match model into honest win probabilities — sampling, convergence, and confidence intervals.
Read →